© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 26017
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and technical certifications or qualifications

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.87
    ьаж
    -0.62
    RenderAtEndOf
    -0.57
    WebVitals
    -0.57
     couverte
    -0.56
    kloped
    -0.56
     magnétique
    -0.55
     solaire
    -0.53
     suivez
    -0.53
     spese
    -0.52
    POSITIVE LOGITS
    stdc
    0.67
    Personendaten
    0.60
    legi
    0.60
    gent
    0.58
    dly
    0.57
    enschappe
    0.55
    illy
    0.54
    yó
    0.54
     Reprodu
    0.53
    enschappelijke
    0.53
    Activations Density 0.226%

    No Known Activations